Optical Neural Network Architecture for Deep Learning with Temporal Synthetic Dimension
Bo Peng1†, Shuo Yan1†, Dali Cheng2, Danying Yu1, Zhanwei Liu1, Vladislav V. Yakovlev3, Luqi Yuan1*, and Xianfeng Chen1,4,5
1State Key Laboratory of Advanced Optical Communication Systems and Networks, School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, China 2Ginzton Laboratory and Department of Electrical Engineering, Stanford University, Stanford, CA 49305, USA 3Texas A&M University, College Station, Texas 77843, USA 4Shanghai Research Center for Quantum Sciences, Shanghai 201315, China 5Collaborative Innovation Center of Light Manipulation and Applications, Shandong Normal University, Jinan 250358, China
Abstract：The physical concept of synthetic dimensions has recently been introduced into optics. The fundamental physics and applications are not yet fully understood, and this report explores an approach to optical neural networks using synthetic dimension in time domain, by theoretically proposing to utilize a single resonator network, where the arrival times of optical pulses are interconnected to construct a temporal synthetic dimension. The set of pulses in each roundtrip therefore provides the sites in each layer in the optical neural network, and can be linearly transformed with splitters and delay lines, including the phase modulators, when pulses circulate inside the network. Such linear transformation can be arbitrarily controlled by applied modulation phases, which serve as the building block of the neural network together with a nonlinear component for pulses. We validate the functionality of the proposed optical neural network for the deep learning purpose with examples handwritten digit recognition and optical pulse train distribution classification problems. This proof of principle computational work explores the new concept of developing a photonics-based machine learning in a single ring network using synthetic dimensions, which allows flexibility and easiness of reconfiguration with complex functionality in achieving desired optical tasks.
Bogaerts W, Pérez D, Capmany J, Miller D A B, Poon J, Englund D, Morichetti F, and Melloni A 2020 Nature586 207
[16]
Xu X Y, Tan M X, Corcoran B, Wu J Y, Boes A, Nguyen T G, Chu S T, Little B E, Hicks D G, Morandotti R, Mitchell A, and Moss D J 2021 Nature589 44
[17]
Feldmann J, Youngblood N, Karpov M, Gehring H, Li X, Stappers M, Gallo M L, Fu X, Lukashchuk A, Raja A S, Liu J, Wright C D, Sebastian A, Kippenberg T J, Pernice W H P, and Bhaskaran H 2021 Nature589 52
Chen C, Ding X, Qin J, He Y, Luo Y H, Chen M C, Liu C, Wang X L, Zhang W J, Li H, You L X, Wang Z, Wang D W, Sanders B C, Lu C Y, and Pan J W 2018 Phys. Rev. Lett.121 100502
[42]
Larger L, Baylón-Fuentes A, Martinenghi R, Udaltsov V S, Chembo Y K, and Jacquot M 2017 Phys. Rev. X7 011015
Duran-Sierra E, Cheng S, Cuenca R, Ahmed B, Ji J, Yakovlev V V, Martinez M, Al-Khalil M, Al-Enazi H, Cheng Y S L, Wright J, Busso C, Jo J A 2021 Cancers13 4751
[61]
Shirshin E A, Gayerm A V, Nikonova E E, Lukina M M, Yakimov B P, Budylin G S, Dudenkova V V, Ignatova N I, Komarov D V, Zagaynova E V, Yakovlev V V, Becker W, Shcheslavskiy V I, Shirmanova M, and Scully M O 2022 Proc. Natl. Acad. Sci. USA119 e2118241119
2023, Vol. 40 
